Skip to main content

Oriol Vinyals: Beyond Deep Learning - Scalable Methods and Models for Learning

Movies Preview

movies
Oriol Vinyals: Beyond Deep Learning - Scalable Methods and Models for Learning


Published October 31, 2013


Talk by Oriol Vinyals, Computer Science Dept. at UC Berkeley. Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.

Abstract
In this talk I will briefly describe several techniques I explored in my thesis that improve how to efficiently model signal representations and learn useful information from them. The building block of my dissertation is based on machine learning approaches to classification, where a (typically non-linear) function is learned from labeled examples to map from signals to some useful information (e.g. an object class present an image, or a word present in an acoustic signal). One of the motivating factors of my work has been advances in neural networks in deep architectures (which has led to the terminology "deep learning"), and that has shown state-of-the-art performance in acoustic modeling and object recognition -- the main focus of this thesis. In my work, I have contributed to both the learning (or training) of such architectures through faster and robust optimization techniques, and also to the simplification of the deep architecture model to an approach that is simple to optimize. Furthermore, I derived a theoretical bound showing a fundamental limitation of shallow architectures based on sparse coding (which can be seen as a one hidden layer neural network), thus justifying the need for deeper architectures, while also empirically verifying these architectural choices on speech recognition. Many of my contributions have been used in a wide variety of applications, products and datasets as a result of many collaborations within ICSI and Berkeley, but also at Microsoft Research and Google Research.


Audio/Visual sound, color

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
Community Video
movies
eye 273
favorite 0
comment 0
Community Media
data
eye 15
favorite 0
comment 0
Community Video
by Kim w. Phillips
movies
eye 42
favorite 0
comment 0
Arxiv.org
by Ludovic Arnold; Yann Ollivier
texts
eye 39
favorite 0
comment 0
Source: http://arxiv.org/abs/1212.1524v2
Arxiv.org
by E. Bylaska; S. Khon; S. Baden; A. Edelman; R. Kawai; M. E. G. Ong; J. H. Weare
texts
eye 28
favorite 0
comment 0
Source: http://arxiv.org/abs/mtrl-th/9412005v1
Community Video
movies
eye 1,114
favorite 0
comment 0